© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 2-GEMMASCOPE-2-TRANSCODER-16K
    4. 715
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    in
    1.30
     nyeri
    1.28
    
    1.26
    ്
    1.26
     Vý
    1.23
    ció
    1.21
    coln
    1.20
     lysed
    1.19
     relatos
    1.19
    kingen
    1.16
    POSITIVE LOGITS
    у
    1.69
    Спасибо
    1.39
    ع
    1.34
    вам
    1.33
    வும்
    1.33
    ધ
    1.26
    retch
    1.23
     abundantly
    1.20
    પ
    1.18
    व
    1.18
    Activations Density 0.585%

    No Known Activations